Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    first-person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lucr
    -0.06
    voří
    -0.06
     glossy
    -0.06
    ора
    -0.06
    課
    -0.06
     сим
    -0.06
    作者
    -0.06
    xlabel
    -0.06
    бер
    -0.06
    getProperty
    -0.06
    POSITIVE LOGITS
    (ac
    0.08
    .Res
    0.07
    (Cl
    0.07
     margins
    0.06
    onsense
    0.06
    NE
    0.06
    _white
    0.06
     needle
    0.06
     T
    0.06
     Tele
    0.06
    Act Density 0.071%

    No Known Activations